AI & Agents MCP servers

34 pay-per-call AI microservices via x402, USDC on Base, no API keys.

Search a registry of agent skills and MCP servers, then run them for real. No install, traced.

Recall your team's coding-agent memory. Install the Assertion plugin to capture it automatically.

Observed facts on public MCP servers: protocol checks, tool changes, signed evidence. No verdicts.

Quality-ranked, cross-platform directory of AI coding skills, plugins and MCP servers.

Pre-execution policy gate for consequential agent actions with durable trust receipts.

Search public agent questions and sourced findings, browse agents, and read the onboarding guide.

Advisory context, intent, budget and API-ledger checks with free examples and x402 payments.

Paid x402 evaluator for evidence, warrant, provenance, and represented action authority.

Choose the safest next action after an API, MCP, or agent failure before retrying.

Caller-specific static MCP capability fit evidence. No live probing; caller owns the decision.

Semantic search for people, projects and AI agents by task, skills and collaboration needs.

Verifiable work for AI agents: every task carries a condition a stranger can execute.

Vet any MCP server before you depend on it. Stamp: PASS, REVIEW, or BLOCK.

Fund or spread Helena's public scientific infrastructure to keep it free to use and independent.

Research Alpha MCP recorder: process X-Rays showing if more AI added independent intelligence.

Agent floor and MCP market: catalog, rack, Stripe checkout, x402, A2A.

A world built and run by AI agents. Join as a citizen: artifacts, quests, governance.

Public NFH knowledge, ownership epochs, versioned learning, Odd Jobs, and unsigned preparation.

Devil's-advocate QC API for AIs: post a decision, get strongest counter-argument. 0.1 USDT/call

Look up independent trust ratings and security, maintenance, and adoption evidence for MCP servers.

Agent-readiness scanner (0-5 score), robots.txt + llms.txt generators, managed agent enablement.

Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.

Discover public AI agents, reusable recipes, and trusted benchmark evidence by task.

Hosted MCP for Conductor Relay: a verifier-backed agent work exchange and cold marketplace.

Autonomous AI microservices: 55 dynamic guardrails, contract audits & oracles via L402/x402/MPP.

Build, run and publish Workbench flows, tasks, shims and knowledge bases.

12 synthetic timesheet exception cases: duplicate payments, policy-watch list entries, missing docum